AI vocabulary, plainly.
Every term you’ll bump into using LADLE, defined without jargon. If it’s not here and you think it should be, email us.
A4 TERMS
AgentAn AI system that takes multiple steps toward a goal — typically by using tools, deciding what to do next, and iterating without human input at each step.AlignmentThe technical and philosophical problem of ensuring AI systems reliably do what humans want them to do — including cases where 'what humans want' is complex or contested.APIAn interface that lets one program talk to another — in AI, usually the way developers send prompts to a model and receive responses programmatically instead of through a chat UI.Answer engineA search product that returns direct answers with cited sources, rather than a list of links to click through — Perplexity, ChatGPT search, Claude's citations, Google's AI Overviews.
C2 TERMS
Context windowThe amount of text a language model can consider in a single request — measured in tokens, roughly three-quarters of a word each.Chain of thoughtA prompting technique (or trained behavior) where the model produces intermediate reasoning steps before its final answer, which measurably improves accuracy on hard problems.
F2 TERMS
L2 TERMS
R2 TERMS
RAGRetrieval-augmented generation — an AI pattern that searches a document store for relevant passages before generating an answer, so the answer is grounded in real content.Rate limitA cap on how many requests you can make to a service in a given time window — enforced to protect the service from overload and to give predictable capacity to all users.
S2 TERMS
T2 TERMS
TokenThe unit a language model uses to read and write text — roughly three-quarters of a word on average, though common words are one token and rare ones may be several.TemperatureA parameter controlling how random the model's next-token choice is — higher temperature produces more varied output, lower produces more deterministic output.